Github user nongli commented on a diff in the pull request:
https://github.com/apache/spark/pull/10435#discussion_r48301323
--- Diff:
sql/catalyst/src/main/scala/org/apache/spark/sql/catalyst/expressions/misc.scala
---
@@ -161,3 +163,197 @@ case class Crc32(child: Expression) extends
UnaryExpression with ImplicitCastInp
})
}
}
+
+/**
+ * A function that calculates hash value for a group of expressions.
+ */
+case class Hash(children: Seq[Expression]) extends Expression {
+
+ override def dataType: DataType = IntegerType
+
+ override def foldable: Boolean = children.forall(_.foldable)
+
+ override def nullable: Boolean = false
+
+ override def eval(input: InternalRow): Any = {
+ var result = 0
+ for (e <- children) {
+ val hashValue = computeHash(e.eval(input), e.dataType)
+ result = result * 31 + hashValue
+ }
+ result
+ }
+
+ private def computeHash(v: Any, dataType: DataType): Int = v match {
+ case null => 0
--- End diff --
Which path handles string?
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
